Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3659 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1413686 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0184. Min Act: -0.0002

Data Index: 583193 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1331895 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1251242 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1471554 (Python Code)

Max Activating Token Index: 604

Text #5

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1310444 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0152. Min Act: -0.0002

Data Index: 394404 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0154. Min Act: -0.0002

Data Index: 217981 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0159. Min Act: -0.0002

Data Index: 247766 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0151. Min Act: -0.0002

Data Index: 218192 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1015262 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1060487 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1352971 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0152. Min Act: -0.0002

Data Index: 290796 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1342306 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1145919 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1580386 (Python Code)

Max Activating Token Index: 910

Text #17

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1229458 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0148. Min Act: -0.0002

Data Index: 208784 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0144. Min Act: -0.0002

Data Index: 431402 (C4 (Web Text))

Max Activating Token Index: 241